Method, device and medium for detecting performance degradation trend of train emergency braking system
By collecting and analyzing the characteristic values of the brake cylinder pressure curve in real time and calculating the degradation factor, the problem of insufficient monitoring of the performance degradation trend of the train emergency braking system is solved, and the detection accuracy and safety are improved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TRAFFIC CONTROL TECH CO LTD
- Filing Date
- 2023-09-13
- Publication Date
- 2026-05-19
AI Technical Summary
Existing technologies lack effective monitoring of the performance degradation trend of train emergency braking systems, resulting in high maintenance costs and risks to train operation safety.
The system collects brake cylinder pressure data in real time during each emergency braking process, generates brake cylinder pressure curves, extracts feature values, calculates degradation factors, and detects performance trends.
This improved the accuracy of degradation detection, enabled continuous monitoring of braking system performance, and enhanced train safety and maintenance efficiency.
Smart Images
Figure CN117387973B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of rail transit technology, and in particular to a method, equipment, and medium for detecting the performance degradation trend of a train emergency braking system. Background Technology
[0002] In modern rail transit, the emergency braking system plays a crucial role in ensuring that trains can safely decelerate and stop in emergency situations. However, with increased usage time and accumulated mileage, the performance of emergency braking systems may degrade, leading to decreased braking effectiveness and potentially causing safety hazards. Therefore, developing a reliable method to detect the performance degradation trend of train emergency braking systems has significant theoretical and practical application value.
[0003] Current technology primarily relies on sensor data to monitor the performance of train braking systems in real time. Typically, parameters such as braking system commands and brake cylinder pressure are recorded in real time, triggering alarms and maintenance based on pre-set thresholds. However, while this method can detect anomalies promptly, it lacks effective monitoring of performance degradation trends. Maintenance measures are usually only taken when performance degradation has become quite severe (or even a malfunction has occurred), leading to high maintenance costs and risks to train safety. Summary of the Invention
[0004] To address one of the aforementioned technical deficiencies, this application provides a method, device, and medium for detecting the performance degradation trend of a train emergency braking system.
[0005] The first aspect of this application provides a method for detecting the performance degradation trend of a train emergency braking system, the method comprising:
[0006] Real-time acquisition of brake cylinder pressure during each emergency braking process generates brake cylinder pressure curves for each emergency braking operation.
[0007] Extract the characteristic values of the brake cylinder pressure curves for each emergency braking operation;
[0008] Based on the predetermined baseline values of the characteristics and the characteristic values of each emergency braking, the degradation factor of each emergency braking is calculated.
[0009] The degradation trend of the train's emergency braking system performance was detected based on the degradation factors of each emergency braking event.
[0010] Optionally, the brake cylinder pressure is collected in real time during each emergency braking process, including:
[0011] Sensors installed at different locations in the braking system begin to collect brake cylinder pressure in real time each time an emergency braking command is issued.
[0012] Optionally, the brake cylinder pressure curve is divided into a build-up phase, a steady phase, and a release phase;
[0013] Extract the characteristic values of the brake cylinder pressure curves for each emergency braking event, including:
[0014] For any emergency braking brake cylinder pressure curve, perform the following steps:
[0015] Extract the slope of the establishment phase, the time from the emergency braking command to the brake cylinder pressure rising to 10% of the target pressure, and the time from the brake cylinder pressure rising to 10% of the target pressure to the brake cylinder pressure rising to 90% of the target pressure.
[0016] Extract the maximum, minimum, mode, and standard deviation of the brake cylinder pressure during the steady-state phase;
[0017] Extract the slope and deviation of the final value from the target final value during the mitigation phase.
[0018] Optionally, before calculating the degradation factor for each emergency braking event based on predetermined baseline values of features and feature values of each emergency braking event, the method further includes:
[0019] Obtain normal values of the characteristics of the braking system under normal performance conditions;
[0020] The mean of the normal values is used as the baseline value for the feature.
[0021] Optionally, based on predetermined baseline values of features and feature values of each emergency braking event, the degradation factor for each emergency braking event is calculated, including:
[0022] The degradation factor for each emergency braking event is calculated using the following formula:
[0023]
[0024] Where t is the identifier of the number of emergency braking operations, and x is the vector formed by the feature values. t Let be the vector formed by the eigenvalues of the t-th emergency braking, μ be the vector formed by the baseline values of the eigenvalues, Σ be the covariance estimate, and W be the weight matrix. t Let be the weight matrix for the t-th emergency braking;
[0025] m is the feature identifier, ω mt Let M be the weight of the m-th feature during the t-th emergency braking, and M be the total number of features.
[0026] Optionally,
[0027] Among them, v mt Let v be the coefficient of variation of the m-th feature during the t-th emergency braking, i be the feature identifier, and v be the variable.it Let be the coefficient of variation of the i-th feature during the t-th emergency braking;
[0028] σ mt Let m be the standard deviation of the m-th feature during the t-th emergency braking. Let m be the mean of the m-th feature during the t-th emergency braking;
[0029] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. This is the normalized value of the m-th feature value during the j-th emergency braking;
[0030] x mj Let μ be the m-th characteristic value of the j-th emergency braking. m Let m be the baseline value for the m-th feature;
[0031] Optionally,
[0032] in, Let be the deviation of the m-th feature during the t-th emergency braking, and let i be the feature identifier. The deviation of the i-th feature during the t-th emergency braking;
[0033] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. μ is the normalized value of the m-th eigenvalue of the j-th emergency braking. m Let m be the baseline value for the m-th feature;
[0034] x mj This is the m-th characteristic value of the j-th emergency braking.
[0035] Optionally, the performance degradation trend of the train's emergency braking system can be detected based on the degradation factors of each emergency braking event, including:
[0036] The degradation factors of each emergency braking event are sorted in chronological order from the oldest to the most recent to form a degradation factor sequence;
[0037] Calculate the degradation trend factor
[0038] Where Avg{} is the mean function, and Adj c [y] is a function that takes c values before and after the center value y, where y is a random variable, Median() is a median function, and g and h are element identifiers of the degradation factor sequence. And (gh)%Δ = 0, where % is the remainder operator and Δ is a predefined interval value.
[0039] A second aspect of this application provides an electronic device, comprising:
[0040] Memory;
[0041] Processor; and
[0042] Computer programs;
[0043] The computer program is stored in the memory and configured to be executed by the processor to implement the method described in the first aspect above.
[0044] A third aspect of this application provides a computer-readable storage medium having a computer program stored thereon; the computer program is executed by a processor to implement the method described in the first aspect above.
[0045] This application provides a method, device, and medium for detecting the performance degradation trend of a train emergency braking system. The method involves real-time acquisition of brake cylinder pressure during each emergency braking process to form brake cylinder pressure curves for each emergency braking; extraction of characteristic values from the brake cylinder pressure curves for each emergency braking; calculation of degradation factors for each emergency braking based on predetermined baseline values of the characteristics and the characteristic values of each emergency braking; and detection of the performance degradation trend of the train emergency braking system based on the degradation factors for each emergency braking.
[0046] The method of this application calculates the degradation factor of each emergency braking based on the brake cylinder pressure during each emergency braking process; and detects the degradation trend of the train's emergency braking system performance based on the degradation factor of each emergency braking. This not only improves the accuracy of degradation detection, but also enables continuous monitoring of the braking system performance, thereby improving the safety of train operation and maintenance efficiency. Attached Figure Description
[0047] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:
[0048] Figure 1 A flowchart illustrating a method for detecting the performance degradation trend of a train emergency braking system provided in this application embodiment;
[0049] Figure 2 This is a schematic diagram of the brake cylinder pressure acquisition principle provided in an embodiment of this application;
[0050] Figure 3 Brake cylinder pressure curves provided for embodiments of this application;
[0051] Figure 4This is a schematic diagram of timing data combination provided in an embodiment of this application;
[0052] Figure 5 A flowchart illustrating another method for detecting the performance degradation trend of a train emergency braking system provided in this application embodiment;
[0053] Figure 6 A timing flowchart illustrating the method for detecting the performance degradation trend of a train emergency braking system provided in this application embodiment. Detailed Implementation
[0054] To make the technical solutions and advantages of the embodiments of this application clearer, the exemplary embodiments of this application will be described in further detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not an exhaustive list of all embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of this application can be combined with each other.
[0055] In developing this application, the inventors discovered that current methods primarily rely on sensor data to monitor the performance of train braking systems in real time. Typically, parameters such as braking system commands and brake cylinder pressure are recorded in real time, and alarms and maintenance are triggered based on pre-set thresholds. However, while this method can detect anomalies promptly, it lacks effective monitoring of performance degradation trends. Maintenance measures are usually only taken when performance degradation has become quite severe, leading to high maintenance costs and risks to train safety.
[0056] To address the aforementioned problems, this application provides a method, device, and medium for detecting the performance degradation trend of a train emergency braking system. The method involves real-time acquisition of brake cylinder pressure during each emergency braking process, forming brake cylinder pressure curves for each emergency braking operation; extracting feature values from these curves; calculating degradation factors for each emergency braking operation based on predetermined feature benchmark values and the feature values of each operation; and detecting the performance degradation trend of the train emergency braking system based on these degradation factors. This method, based on the brake cylinder pressure during each emergency braking operation, calculates the degradation factors for each operation and detects the performance degradation trend of the train emergency braking system based on these degradation factors. This not only improves the accuracy of degradation detection but also enables continuous monitoring of the braking system performance, thereby improving train operation safety and maintenance efficiency.
[0057] See Figure 1 The implementation process of the train emergency braking system performance degradation trend detection method provided in this embodiment is as follows:
[0058] 101. Real-time acquisition of brake cylinder pressure during each emergency braking process to generate brake cylinder pressure curves for each emergency braking operation.
[0059] Specifically, sensors installed at different locations in the braking system begin to collect brake cylinder pressure in real time each time an emergency braking command is issued.
[0060] For example, corresponding sensors (such as instruments) are installed at key locations in the braking system of the train. During the emergency braking process, the sensors collect the brake cylinder pressure in real time to obtain accurate brake cylinder pressure change data and form a brake cylinder pressure change curve.
[0061] The data collection process is as follows: Figure 2 As shown, the emergency braking system is treated as a black box, with only the brake cylinder pressure being detected.
[0062] The brake cylinder pressure variation curve is a graph describing how the brake cylinder pressure changes over time, reflecting the performance and dynamic characteristics of the emergency braking system. During emergency braking, the brake cylinder pressure curve undergoes a series of changes, including the initial applied brake pressure, the stable maintenance of the brake cylinder pressure, and the pressure changes during brake release.
[0063] A typical brake cylinder pressure change curve is as follows: Figure 3 As shown, when an emergency braking command is issued, the brake cylinder pressure begins to rise from 0 and stabilizes near the target value. When the command is revoked, the pressure begins to drop.
[0064] Therefore, based on the collected brake cylinder pressure data, the braking process can be divided into three phases: the build-up phase, the steady-state phase, and the release phase. The build-up phase represents a rapid increase in brake cylinder pressure, the steady-state phase represents pressure stabilizing near the target value, and the release phase represents a rapid decrease in brake cylinder pressure. Correspondingly, the brake cylinder pressure curve is also divided into these three phases.
[0065] 102. Extract the characteristic values of the brake cylinder pressure curves for each emergency braking operation.
[0066] The brake cylinder pressure curve is divided into three stages: the establishment stage, the stabilization stage, and the release stage. The feature values extracted for each stage are different. This step will extract the feature values for each stage of the brake cylinder pressure curve for each emergency braking.
[0067] For example, the brake cylinder pressure curve for any emergency braking operation:
[0068] • For the establishment phase
[0069] Extract the slope of the establishment phase, the time from the emergency braking command to the brake cylinder pressure rising to 10% of the target pressure (e.g., 10%T), and the time from the brake cylinder pressure rising to 10% of the target pressure to the brake cylinder pressure rising to 90% of the target pressure (e.g., 90%T).
[0070] 10%T: The time required for the brake cylinder pressure to rise to 10% of the target pressure under an emergency braking command. This reflects the performance during the initial build-up phase.
[0071] 90%T: The time required for the brake cylinder pressure to rise from 10% to 90% of the target pressure. This reflects the performance in the later stages of the build-up phase.
[0072] The slope of the establishment phase: This feature reflects the rate at which the pressure rises during the establishment phase as a whole.
[0073] • For the stable phase
[0074] Extract the maximum, minimum, mode, and standard deviation of the brake cylinder pressure during the steady-state phase.
[0075] Mode: The most frequent data value during the stable phase is selected as the mode.
[0076] Standard deviation: Standard deviation can be used to represent the degree of fluctuation in brake cylinder pressure values.
[0077] Maximum and minimum values: The maximum and minimum pressure values during the steady-state phase. This characteristic reflects whether pressure overshoot or undershoot has occurred.
[0078] • For the relief phase
[0079] Extract the slope and deviation of the final value from the target final value during the mitigation phase.
[0080] Slope of the relief phase: This feature reflects the rate of pressure reduction during the relief phase as a whole.
[0081] Deviation between the final value and the target final value during the mitigation phase: This feature reflects the deviation between the final value during the mitigation phase and the target final value (where the target final value is generally 0). Excessive deviation indicates an abnormal mitigation process.
[0082] 103. Based on the predetermined baseline values of the characteristics and the characteristic values of each emergency braking, calculate the degradation factor of each emergency braking.
[0083] Before executing step 103, the baseline values for each feature are determined, that is, the values of each feature under normal conditions. These feature values are the same as those in step 102. There are two methods for determining the baseline values: the first is to use relevant technical specifications; the second is to obtain the normal values of the features under normal braking system performance and determine the average of these normal values as the baseline value for the feature.
[0084] For the second approach, normal values of features under normal conditions are collected, and the average value method is used to establish the baseline value of the features.
[0085] For example, m is the feature identifier, a is the identifier for collecting normal values of the feature under normal conditions, n is the total number of times the normal values of the feature are collected under normal conditions, and x ma If the normal value of the m-th feature is obtained from the a-th acquisition under normal conditions, then the final baseline value of the m-th feature is...
[0086] It should be noted that the process of determining the baseline value is not a necessary step to be performed every time the method provided in this embodiment is executed. It is only necessary to determine the baseline value when the method provided in this embodiment is executed for the first time. Subsequently, the baseline value determination process is executed again when the baseline value determination conditions are met (such as a change in features, or a baseline value determination is performed every preset time period, or other conditions).
[0087] The degradation factor calculated in step 103 is used to quantify the performance state of the emergency braking system. During actual data acquisition, calculating the degradation factor helps to accurately assess changes in system performance. To calculate the degradation factor more accurately, the method provided in this embodiment introduces a weighted approach to improve its performance. Specifically, the degradation factor for each emergency braking event is calculated using the following formula:
[0088]
[0089] Where t is the identifier of the number of emergency braking operations, and x is the vector formed by the feature values. t Let be the vector formed by the feature values of the t-th emergency braking, μ be the vector formed by the baseline feature values, Σ be the covariance estimate (which can be calculated based on the baseline feature set or set manually), and W be the weight matrix. t Let be the weight matrix for the t-th emergency braking (which is a diagonal matrix).
[0090] m is the feature identifier, ω mt Let M be the weight of the m-th feature during the t-th emergency braking, and M be the total number of features.
[0091] In the process of calculating the degradation factor It indicates the degree of deviation of new data from the normal state. It can measure the distance between sample points and multivariate distributions and can eliminate the interference of correlation between variables. Adjusting the importance of different dimensions in the feature vector helps to better consider the correlation and importance between features when calculating the degree of deviation, thus adapting to different feature variation patterns. Therefore, a larger degradation factor means that the performance of the emergency braking system deviates more from the normal state.
[0092] Where, ω mt There are two methods for determining this.
[0093] The first determination method: using the coefficient of variation to calculate...
[0094] Right now
[0095] Among them, v mt Let v be the coefficient of variation of the m-th feature during the t-th emergency braking, i be the feature identifier, and v be the variable. it Let be the coefficient of variation of the i-th feature during the t-th emergency braking.
[0096] σ mt Let m be the standard deviation of the m-th feature during the t-th emergency braking. Let m be the mean of the m-th feature during the t-th emergency braking.
[0097] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. It is the normalized value of the m-th feature value of the j-th emergency braking.
[0098] x mj Let μ be the m-th characteristic value of the j-th emergency braking. m This is the baseline value for the m-th feature.
[0099] In practical implementation, it is possible
[0100] 1.1 Usage Normalize the feature set of the benchmark data.
[0101] 1.2 Calculation of coefficient of variation in,
[0102] 1.3 Calculate the weights
[0103] The second determination method: using deviation calculation.
[0104] Right now
[0105] in, Let be the deviation of the m-th feature during the t-th emergency braking, and let i be the feature identifier. This represents the deviation of the i-th feature during the t-th emergency braking.
[0106] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. μ is the normalized value of the m-th eigenvalue of the j-th emergency braking. m This is the baseline value for the m-th feature.
[0107] x mj This is the m-th characteristic value of the j-th emergency braking.
[0108] In practical implementation, it is possible
[0109] 2.1 Usage Normalize the feature set of the benchmark data.
[0110] 2.2 Calculation of Deviation
[0111] 2.3 Calculate the weights
[0112] 104. The degradation trend of the train's emergency braking system performance was detected based on the degradation factors of each emergency braking event.
[0113] After steps 101 to 103, the degradation factor for each emergency braking operation can be obtained. To detect whether the emergency braking system exhibits a degradation trend, step 104 will sort the degradation factors according to the acquisition time, forming a time series with a window size of b. For example, a schematic diagram of the time series data combination with b=6 is shown below. Figure 4 As shown, during step 104, the degradation factors of each emergency braking event are sorted chronologically from oldest to youngest based on the time of occurrence, forming a degradation factor sequence, for example, a degradation factor sequence {d1,…,d...}. h ,…,d g ,…}。 Calculate the degradation trend factor
[0114] Where Avg{} is the mean function, and Adj c [y] is a function that takes c values before and after the center value y (c is a pre-set value, which can be an empirical value), where y is a random variable, Median() is the median function, and g and h are the element identifiers of the degradation factor sequence. And (gh)%Δ = 0, where % is the remainder operator and Δ is a predefined interval value.
[0115] Although a gradual increase in the degradation factor indicates system degradation, the degradation factor may fluctuate, making it difficult to determine whether system degradation has occurred. Therefore, this step incorporates a characterizing factor of the slope. By performing degradation trend detection, the problem of difficulty in determining degradation due to fluctuations is solved. This represents the average rate of change and trend of the degradation factor sequence, when At that time, the degradation factor sequence showed an upward trend; when At that time, the trend of the degradation factor sequence was not obvious; when At that time, the degradation factor sequence showed a downward trend.
[0116] However, calculating the slope of data point pairs using the median function and selecting the median as the final trend estimate requires calculating the slope for each data pair, resulting in a huge computational burden. Therefore, this step reduces the computational burden by setting an interval value Δ. And (gh)%Δ=0.
[0117] Furthermore, since using the median may cause result bias and instability, this step uses the average value instead of the median. However, if the entire slope is included in the calculation, it becomes sensitive to outliers and noise. Therefore, this step ultimately uses the local mean method to calculate the slope, i.e. And (gh)%Δ=0.
[0118] When using local mean, the slope of each pair of data is first calculated, then the data are arranged from smallest to largest, and then the average of c values near the median is taken.
[0119] For example, given a list of data arranged in ascending order [0, 0.05, 0.07, 0.08, 0.1, 0.13, 0.14, 0.19, 0.21], where the value is 0.1, if we take c = 4, then the c values near the median are [0, 0.05, 0.07, 0.08, 0.1, 0.13, 0.14, 0.19, 0.21] (the bold text represents the median, and the italics represent the four values near the median).
[0120] Its mean is (0.07+0.08+0.1+0.13+0.14) / (c+1)=0.104.
[0121] β reflects the trend of the sequence. If β > 0, it indicates that the sequence is trending upwards, but a small upward trend may not necessarily indicate degradation. To more accurately determine whether degradation has occurred, a degradation threshold θ can be introduced. When β > θ, it indicates that degradation has occurred.
[0122] By using the degradation threshold θ, we can filter out those with a significant upward trend, thus more accurately determining whether the performance of the emergency braking system has degraded.
[0123] The train emergency braking system performance degradation trend detection method provided in this embodiment can improve the accuracy of degradation detection and realize continuous monitoring of braking system performance, thereby improving train operation safety and maintenance efficiency.
[0124] The train emergency braking system is a critical component of the train safety system, used to rapidly decelerate or stop the train in emergency situations. It is a vital protective device designed to ensure the safety of the train and its passengers. When emergency braking is triggered, the braking command causes a rapid increase in brake cylinder pressure, pushing the piston and, via a transmission mechanism, pressing the brake shoes against the wheels to decelerate or stop the train. Given the potential differences between different types of trains and braking systems, the train emergency braking system performance degradation trend detection method provided in this embodiment treats the emergency braking system as a black box, only detecting the brake cylinder pressure (e.g., ...). Figure 2 (as shown), and features are extracted from it to calculate the degradation factor. To detect trends, the current degradation factor is combined with the degradation factors within the window to form time-series data (such as...). Figure 4 As shown in the figure, and trend detection is performed.
[0125] The train emergency braking system performance degradation trend detection method provided in this embodiment is applicable to different types of trains and braking systems, and can meet the needs of modern rail transportation systems for braking system status monitoring and maintenance management, thereby ensuring the safety and stability of trains. Through this method, train operators can identify and resolve problems before performance degradation worsens, reducing maintenance costs and improving system reliability.
[0126] In practical implementation, it can be as follows: Figure 5 As shown, data acquisition is performed in step 101, feature extraction is performed in step 102, degradation factor is calculated based on the feature extraction results and pre-obtained benchmark values in step 103, and trend detection is performed in step 104. The corresponding time-series flowchart is shown below. Figure 6 As shown in the figure. The train emergency braking system performance degradation trend detection method provided in this embodiment can detect early signs of degradation in the emergency braking system in a timely manner, thereby ensuring the reliability and safety of the system. The train emergency braking system performance degradation trend detection method provided in this embodiment not only helps to ensure the safety of train operation, but also provides strong support for maintenance and safety.
[0127] This embodiment provides a method for detecting the performance degradation trend of a train emergency braking system. It involves real-time acquisition of brake cylinder pressure during each emergency braking process, forming brake cylinder pressure curves for each emergency braking event; extracting feature values from these curves; calculating degradation factors for each emergency braking event based on predetermined feature benchmark values and the feature values of each event; and detecting the performance degradation trend of the train emergency braking system based on these degradation factors. This method, based on brake cylinder pressure during each emergency braking event, calculates degradation factors for each event and detects performance degradation trends based on these factors. This not only improves the accuracy of degradation detection but also enables continuous monitoring of the braking system performance, thereby improving train operation safety and maintenance efficiency.
[0128] Based on the same inventive concept as the method for detecting the performance degradation trend of a train emergency braking system, this embodiment provides an electronic device, which includes: a memory, a processor, and a computer program.
[0129] The computer program is stored in memory and configured to be executed by a processor to implement the above-mentioned method for detecting the performance degradation trend of the train emergency braking system.
[0130] Specifically,
[0131] The brake cylinder pressure is collected in real time during each emergency braking process, and the brake cylinder pressure curve for each emergency braking is generated.
[0132] Extract the characteristic values of the brake cylinder pressure curves for each emergency braking operation.
[0133] The degradation factor for each emergency braking event is calculated based on the predetermined baseline values of the characteristics and the characteristic values of each emergency braking event.
[0134] The degradation trend of the train's emergency braking system performance was detected based on the degradation factors of each emergency braking event.
[0135] Optionally, the brake cylinder pressure is collected in real time during each emergency braking process, including:
[0136] Sensors installed at different locations in the braking system begin to collect brake cylinder pressure in real time each time an emergency braking command is issued.
[0137] Optionally, the brake cylinder pressure curve is divided into a build-up phase, a steady phase, and a release phase.
[0138] Extract the characteristic values of the brake cylinder pressure curves for each emergency braking event, including:
[0139] For any emergency braking brake cylinder pressure curve, perform the following steps:
[0140] Extract the slope of the establishment phase, the time from the emergency braking command to the brake cylinder pressure rising to 10% of the target pressure, and the time from the brake cylinder pressure rising to 10% of the target pressure to the brake cylinder pressure rising to 90% of the target pressure.
[0141] Extract the maximum, minimum, mode, and standard deviation of the brake cylinder pressure during the steady-state phase.
[0142] Extract the slope and deviation of the final value from the target final value during the mitigation phase.
[0143] Optionally, before calculating the degradation factor for each emergency braking event based on predetermined baseline values of features and feature values of each emergency braking event, the method further includes:
[0144] Obtain the normal values of the characteristics of the braking system under normal performance conditions.
[0145] The mean of the normal values is used as the baseline value for the feature.
[0146] Optionally, based on predetermined baseline values of features and feature values of each emergency braking event, the degradation factor for each emergency braking event is calculated, including:
[0147] The degradation factor for each emergency braking event is calculated using the following formula:
[0148]
[0149] Where t is the identifier of the number of emergency braking operations, and x is the vector formed by the feature values. t Let be the vector formed by the eigenvalues of the t-th emergency braking, μ be the vector formed by the baseline values of the eigenvalues, Σ be the covariance estimate, and W be the weight matrix. t Let be the weight matrix for the t-th emergency braking.
[0150] m is the feature identifier, ω mt Let M be the weight of the m-th feature during the t-th emergency braking, and M be the total number of features.
[0151] Optionally,
[0152] Among them, v mt Let v be the coefficient of variation of the m-th feature during the t-th emergency braking, i be the feature identifier, and v be the variable. it Let be the coefficient of variation of the i-th feature during the t-th emergency braking.
[0153] σ mt Let m be the standard deviation of the m-th feature during the t-th emergency braking. Let m be the mean of the m-th feature during the t-th emergency braking.
[0154] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. It is the normalized value of the m-th feature value of the j-th emergency braking.
[0155] x mj Let μ be the m-th characteristic value of the j-th emergency braking. m This is the baseline value for the m-th feature.
[0156] Optionally,
[0157] in, Let be the deviation of the m-th feature during the t-th emergency braking, and let i be the feature identifier. This represents the deviation of the i-th feature during the t-th emergency braking.
[0158] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. μ is the normalized value of the m-th eigenvalue of the j-th emergency braking. m This is the baseline value for the m-th feature.
[0159] x mj This is the m-th characteristic value of the j-th emergency braking.
[0160] Optionally, the performance degradation trend of the train's emergency braking system can be detected based on the degradation factors of each emergency braking event, including:
[0161] The degradation factors of each emergency braking event are sorted in chronological order from the furthest to the most recent to form a degradation factor sequence.
[0162] Calculate the degradation trend factor
[0163] Where Avg{} is the mean function, and Adj c [y] is a function that takes c values before and after the center value y, where y is a random variable, Median() is a median function, and g and h are element identifiers of the degradation factor sequence. And (gh)%Δ = 0, where % is the remainder operator and Δ is a predefined interval value.
[0164] The electronic device provided in this embodiment has a computer program executed by a processor to calculate the degradation factor of each emergency braking based on the brake cylinder pressure during each emergency braking process. The degradation factor of each emergency braking is used to detect the performance degradation trend of the train's emergency braking system, which not only improves the accuracy of degradation detection, but also realizes continuous monitoring of the braking system performance, thereby improving the safety of train operation and maintenance efficiency.
[0165] Based on the same inventive concept as the method for detecting the performance degradation trend of a train emergency braking system, this embodiment provides a computer-readable storage medium on which a computer program is stored. The computer program is executed by a processor to implement the aforementioned method for detecting the performance degradation trend of a train emergency braking system.
[0166] Specifically,
[0167] The brake cylinder pressure is collected in real time during each emergency braking process, and the brake cylinder pressure curve for each emergency braking is generated.
[0168] Extract the characteristic values of the brake cylinder pressure curves for each emergency braking operation.
[0169] The degradation factor for each emergency braking event is calculated based on the predetermined baseline values of the characteristics and the characteristic values of each emergency braking event.
[0170] The degradation trend of the train's emergency braking system performance was detected based on the degradation factors of each emergency braking event.
[0171] Optionally, the brake cylinder pressure is collected in real time during each emergency braking process, including:
[0172] Sensors installed at different locations in the braking system begin to collect brake cylinder pressure in real time each time an emergency braking command is issued.
[0173] Optionally, the brake cylinder pressure curve is divided into a build-up phase, a steady phase, and a release phase.
[0174] Extract the characteristic values of the brake cylinder pressure curves for each emergency braking event, including:
[0175] For any emergency braking brake cylinder pressure curve, perform the following steps:
[0176] Extract the slope of the establishment phase, the time from the emergency braking command to the brake cylinder pressure rising to 10% of the target pressure, and the time from the brake cylinder pressure rising to 10% of the target pressure to the brake cylinder pressure rising to 90% of the target pressure.
[0177] Extract the maximum, minimum, mode, and standard deviation of the brake cylinder pressure during the steady-state phase.
[0178] Extract the slope and deviation of the final value from the target final value during the mitigation phase.
[0179] Optionally, before calculating the degradation factor for each emergency braking event based on predetermined baseline values of features and feature values of each emergency braking event, the method further includes:
[0180] Obtain the normal values of the characteristics of the braking system under normal performance conditions.
[0181] The mean of the normal values is used as the baseline value for the feature.
[0182] Optionally, based on predetermined baseline values of features and feature values of each emergency braking event, the degradation factor for each emergency braking event is calculated, including:
[0183] The degradation factor for each emergency braking event is calculated using the following formula:
[0184]
[0185] Where t represents the number of emergency braking events, x is the vector formed by the eigenvalues, xt is the vector formed by the eigenvalues of the t-th emergency braking event, μ is the vector formed by the baseline values of the eigenvalues, Σ is the covariance estimate, and W is the weight matrix. t Let be the weight matrix for the t-th emergency braking.
[0186] m is the feature identifier, ω mt Let M be the weight of the m-th feature during the t-th emergency braking, and M be the total number of features.
[0187] Optionally,
[0188] Among them, v mt Let v be the coefficient of variation of the m-th feature during the t-th emergency braking, i be the feature identifier, and v be the variable. it Let be the coefficient of variation of the i-th feature during the t-th emergency braking.
[0189] σ mt Let m be the standard deviation of the m-th feature during the t-th emergency braking. Let m be the mean of the m-th feature during the t-th emergency braking.
[0190] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. It is the normalized value of the m-th feature value of the j-th emergency braking.
[0191] x mj Let μ be the m-th characteristic value of the j-th emergency braking. m This is the baseline value for the m-th feature.
[0192] Optionally,
[0193] in, Let be the deviation of the m-th feature during the t-th emergency braking, and let i be the feature identifier. This represents the deviation of the i-th feature during the t-th emergency braking.
[0194] j is the identifier for the number of emergency braking events, j = 1, 2, ..., t. μ is the normalized value of the m-th eigenvalue of the j-th emergency braking. m This is the baseline value for the m-th feature.
[0195] x mj This is the m-th characteristic value of the j-th emergency braking.
[0196] Optionally, the performance degradation trend of the train's emergency braking system can be detected based on the degradation factors of each emergency braking event, including:
[0197] The degradation factors of each emergency braking event are sorted in chronological order from the furthest to the most recent to form a degradation factor sequence.
[0198] Calculate the degradation trend factor
[0199] Where Avg{} is the mean function, and Adj c [y] is a function that takes c values before and after the center value y, where y is a random variable, Median() is a median function, and g and h are element identifiers of the degradation factor sequence. And (gh)%Δ = 0, where % is the remainder operator and Δ is a predefined interval value.
[0200] The computer-readable storage medium provided in this embodiment has a computer program thereon that is executed by a processor to calculate the degradation factor of each emergency braking operation based on the brake cylinder pressure during each emergency braking operation. The degradation factor of each emergency braking operation is used to detect the performance degradation trend of the train's emergency braking system, which not only improves the accuracy of degradation detection, but also enables continuous monitoring of the braking system performance, thereby improving the safety of train operation and maintenance efficiency.
[0201] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of this application can be implemented in various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.
[0202] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0203] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0204] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0205] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.
[0206] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. A method for detecting the performance degradation trend of a train emergency braking system, characterized in that, The method includes: Real-time acquisition of brake cylinder pressure during each emergency braking process generates brake cylinder pressure curves for each emergency braking operation. Extract the characteristic values of the brake cylinder pressure curves for each emergency braking operation; Based on the predetermined baseline values of the characteristics and the characteristic values of each emergency braking, the degradation factor of each emergency braking is calculated. The degradation trend of the train's emergency braking system performance was detected based on the degradation factors of each emergency braking event. The brake cylinder pressure curve is divided into three stages: the establishment stage, the stabilization stage, and the release stage. The extraction of feature values from the brake cylinder pressure curves for each emergency braking event includes: For any emergency braking brake cylinder pressure curve, perform the following steps: Extract the slope of the establishment phase, the time from the emergency braking command to the brake cylinder pressure rising to 10% of the target pressure, and the time from the brake cylinder pressure rising to 10% of the target pressure to the brake cylinder pressure rising to 90% of the target pressure. Extract the maximum, minimum, mode, and standard deviation of the brake cylinder pressure during the steady-state phase; Extract the slope and deviation of the final value from the target final value during the mitigation phase; The calculation of the degradation factor for each emergency braking event, based on predetermined baseline values of features and feature values of each emergency braking event, includes: The degradation factor for each emergency braking event is calculated using the following formula: ； in, This is to indicate the number of emergency braking operations. The vector formed by the eigenvalues For the first The vector formed by the eigenvalues of the second emergency braking A vector formed by the baseline values of the features. For covariance estimation, This is the weight matrix. For the first The weight matrix for the second emergency braking; , For feature identification, For the first The first emergency braking The weights of each feature The total number of features; The method of detecting the performance degradation trend of the train's emergency braking system based on degradation factors from each emergency braking operation includes: The degradation factors of each emergency braking event are sorted in chronological order from the oldest to the most recent to form a degradation factor sequence; Calculate the degradation trend factor ; in, To obtain the mean function, For Take the value as the center and take the front and back. Value function, For random variables, To take the median function, and Element identifier for the degradation factor sequence. ,and , The remainder operator. For predefined interval values.
2. The method according to claim 1, characterized in that, The real-time acquisition of brake cylinder pressure during each emergency braking process includes: Sensors installed at different locations in the braking system begin to collect brake cylinder pressure in real time each time an emergency braking command is issued.
3. The method according to claim 1, characterized in that, Before calculating the degradation factor for each emergency braking event based on predetermined baseline values of features and feature values of each emergency braking event, the method further includes: Obtain normal values of the characteristics of the braking system under normal performance conditions; The mean of the normal values is used as the baseline value for the feature.
4. The method according to claim 1, characterized in that, ； in, For the first The first emergency braking The coefficient of variation of each feature For feature identification, For the first The first emergency braking The coefficient of variation of each feature; , For the first The first emergency braking The standard deviation of each feature For the first The first emergency braking The mean of each feature; , This is to indicate the number of emergency braking operations. , For the first The first emergency braking Normalized values of eigenvalues; , For the first The first emergency braking 1 eigenvalue, For the first The baseline value for each feature; .
5. The method according to claim 1, characterized in that, ； in, For the first The first emergency braking Deviation of each feature, For feature identification, For the first The first emergency braking Deviation of each characteristic; , This is to indicate the number of emergency braking operations. , For the first The first emergency braking Normalized values of each eigenvalue For the first The baseline value for each feature; , For the first The first emergency braking Each feature value.
6. An electronic device, characterized in that, include: Memory; processor; as well as Computer programs; The computer program is stored in the memory and configured to be executed by the processor to implement the method as described in any one of claims 1-5.
7. A computer-readable storage medium, characterized in that, It stores a computer program thereon; the computer program is executed by a processor to implement the method as described in any one of claims 1-5.